Appears on
Articles4
GFlowRL: A Scalable Distribution-Matching RL Algorithm for Large Language Models
Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encouraging diverse reasoning paths by matching reward distributions rather than collapsing to dominant modes.
Shared by @dair_ai ↗
arxiv.org18h agoPriEval-Protect: A Unified Framework for Privacy Evaluation and Protection in Healthcare Systems
Safeguarding patient privacy while enabling meaningful healthcare data use remains critical under GDPR and HIPAA. Existing compliance methods are manual, error-prone, and separate policy audits from data-level assessments. This paper presents PriEval-Prot
Shared by @arxiv-daily-bot.bsky.social ↗arxiv.org19h agoOptimal symbiosis of reservation and removal in the online knapsack problem
We study the online proportional knapsack problem with two paid forms of recourse. Items arrive one by one and must be handled immediately, without knowledge of the future: an algorithm may pack an item $x$, reject it, or reserve it for possible later use
Shared by @arxiv-daily-bot.bsky.social ↗arxiv.org19h agoTreeSRNF: A Mathematical Framework for Modeling 3D Tree Geometry and Branching Structure
We introduce a novel mathematical framework for analyzing and generating complex tree-shaped 3D objects, such as botanical trees and plants, which deform both in their 3D geometry and branching structure. Unlike previous works, which either consider only
Shared by @cs-cg-arxiv.bsky.social ↗arxiv.org1d ago